Entry Barriers, Predictive AI Models, and Innovative Student Retention Strategies in Higher Education in Esmeraldas
DOI:
https://doi.org/10.70577/asce.v5i1.682Keywords:
Higher education, Student retention, Dropout prediction, Learning analytics, Educational data mining, Early warning systems.Abstract
This literature review examines barriers to entry, AI-based predictive models, and innovative student retention strategies in higher education, emphasizing institutional applicability to the Universidad Técnica Luis Vargas Torres de Esmeraldas. Evidence indicates that retention is shaped by structural entry barriers and early academic vulnerability, and that predictive performance depends strongly on data availability and timing. Models trained “from day one” using enrollment data provide operationally useful but moderate accuracy, while models fed with learning management system traces improve substantially as behavioral evidence accumulates across weeks. Findings also show that prediction becomes institutionally meaningful only when embedded in a closed-loop process that links early identification to timely feedback and tailored support actions. Interventions such as early warning messaging, targeted outreach, and technology-mediated assistance (e.g., chatbots) are associated with improvements in engagement and academic outcomes, suggesting scalable pathways for first-year support. Discussion-focused studies underline that learning analytics must be interpreted cautiously, given the multi-dimensional nature of engagement, and must be governed through transparent data practices, privacy safeguards, ethical legitimacy, and fairness auditing to avoid differential harms across student subgroups. Overall, the review supports a phased institutional strategy combining entry profiling, progressively updated risk prediction, explainability, and a portfolio of evaluable interventions aligned with student support services and financial aid mechanisms.
Downloads
References
Bañeres, D., Rodríguez-González, M. E., Guerrero-Roldán, A.-E., & Cortadas, P. (2023). An early warning system to identify and intervene online dropout learners. International Journal of Educational Technology in Higher Education, 20, Article 3. https://doi.org/10.1186/s41239-022-00371-5
Bergdahl, N., Bond, M., Sjöberg, J., Dougherty, M., & Oxley, E. (2024). Unpacking student engagement in higher education learning analytics: A systematic review. International Journal of Educational Technology in Higher Education, 21, Article 63. https://doi.org/10.1186/s41239-024-00493-y
Berlanga, V., & Corti, F. (2025). Impact of scholarships on university academic performance: A comparative analysis of students with and without scholarships. Frontiers in Education, 10, 1554073. https://doi.org/10.3389/feduc.2025.1554073
Carballo-Mendívil, B., Arellano-González, A., Ríos-Vázquez, N. J., & Lizardi-Duarte, M. P. (2025). Predicting student dropout from day one: XGBoost-based early warning system for higher education institutions. Applied Sciences, 15(16), 9202. https://doi.org/10.3390/app15169202
Chang, Y.-H., Chang, W.-H., & Chang, C.-Y. (2025). Developing an early warning system for at-risk students in higher education with tailored interventions. Education Sciences, 15(10), 1321. https://doi.org/10.3390/educsci15101321
Dai, W., Lin, J., Jin, F. J.-Y., Tsai, Y.-S., Srivastava, N., Le Bodic, P., Gašević, D., & Chen, G. (2025). Learning analytics for early identification of at-risk students and feedback intervention. Journal of Learning Analytics, 12(3), 102–125. https://doi.org/10.18608/jla.2025.8735
de Oliveira, C. F., Sobral, S. R., Ferreira, M. J., & Moreira, F. (2021). How does learning analytics contribute to prevent students’ dropout in higher education: A systematic literature review. Big Data and Cognitive Computing, 5(4), 64. https://doi.org/10.3390/bdcc5040064
de Vreugd, L., van Leeuwen, A., Jansen, R., & van der Schaaf, M. (2024). Learning analytics dashboard design and evaluation to support student self-regulation of study behaviour. Journal of Learning Analytics, 11(3), 249–262. https://doi.org/10.18608/jla.2024.8529
Dixon, E., Howe, H., & Richter, S. (2025). Exploring learning analytics practices and their benefits through the lens of three case studies in UK higher education. Research in Learning Technology, 33, 3127. https://doi.org/10.25304/rlt.v33.3127
Essel, H. B., Vlachopoulos, D., Tachie-Menson, A., Johnson, E. E., & Baah, P. K. (2022). The impact of a virtual teaching assistant (chatbot) on students’ learning in Ghanaian higher education. International Journal of Educational Technology in Higher Education, 19, Article 57. https://doi.org/10.1186/s41239-022-00362-6
Guzmán-Valenzuela, C., Gómez-González, C., Rojas-Murphy Tagle, A., et al. (2021). Learning analytics in higher education: A preponderance of analytics but very little learning? International Journal of Educational Technology in Higher Education, 18, 23. https://doi.org/10.1186/s41239-021-00258-x
Ifenthaler, D., & Yau, J. Y.-K. (2020). Utilising learning analytics to support study success in higher education: A systematic review. Educational Technology Research and Development, 68, 1961–1990. https://doi.org/10.1007/s11423-020-09788-z
Imundo, C., Ferrante, L., De Iulio, C., & Blasi, C. (2025). Student knowledge of and responses to an early alert system: An assessment for improvement. Applied Sciences, 15(11), 6316. https://doi.org/10.3390/app15116316
Jagačić, T., Dragičević, N., & Drljača, N. (2024). Students’ perceptions of the ethical aspects of learning analytics. TEM Journal, 13(4), 3526–3535. https://doi.org/10.18421/TEM134-85
Kabathova, J., & Drlik, M. (2021). Towards educational data mining: Predicting student dropout in university courses using different machine learning techniques. Applied Sciences, 11(7), 3130. https://doi.org/10.3390/app11073130
Kesgin, K., Kiraz, S., Kosunalp, S., & Stoycheva, B. (2025). Beyond performance: Explaining and ensuring fairness in student academic performance prediction with machine learning. Applied Sciences, 15(15), 8409. https://doi.org/10.3390/app15158409
Linden, C. (2022). Engagement with targeted support and student retention: Evidence from an early intervention. Student Success, 13(1), 67–73. https://doi.org/10.5204/ssj.2152
Liu, H., et al. (2025). Model interpretability on private-safe oriented student dropout risk prediction in higher education. PLOS ONE, 20(2), e0317726. https://doi.org/10.1371/journal.pone.0317726
Liu, Y., Wang, W., & Xu, E. (2025). The effectiveness of learning analytics-based interventions in enhancing students’ learning effect: A meta-analysis of empirical studies. SAGE Open, 15(2), 21582440251336707. https://doi.org/10.1177/21582440251336707
Logroño, P. F. B. (2025). Acceso a la educación superior en Ecuador: una deuda de la administración pública. Perspectivas Sociales y Administrativas, 3(2), 56–66. https://doi.org/10.61347/psa.v3i2.93
Mustofa, S., Emon, Y. R., Mamun, S. B., et al. (2025). A novel AI-driven model for student dropout risk analysis with explainable AI insights. Computers and Education: Artificial Intelligence, 8, 100352. https://doi.org/10.1016/j.caeai.2024.100352
Rebelo Marcolino, M., Reis Porto, T., Thompsen Primo, T., Targino, R., Ramos, V., Marques Queiroga, E., Munoz, R., & Cechinel, C. (2025). Student dropout prediction through machine learning optimization: Insights from Moodle log data. Scientific Reports, 15, Article 9840. https://doi.org/10.1038/s41598-025-93918-1
Rodas, M. P., Gomez, A. H., & Stefos, E. (2023). La admisión y retención universitaria: caso ecuatoriano en la Universidad Nacional de Educación. Revista de la Educación Superior, 52(208). https://doi.org/10.36857/resu.2023.208.2656
Romero, S., et al. (2025). Statistical and machine learning models for predicting students’ dropout risk: The effect of scholarship programs. PLOS ONE, 20(6), e0325047. https://doi.org/10.1371/journal.pone.0325047
Shafiq, D. A., Marjani, M., Habeeb, R. A. A., & Asirvatham, D. (2022). Student retention using educational data mining and predictive analytics: A systematic literature review. IEEE Access, 10. https://doi.org/10.1109/ACCESS.2022.3188767
Silva-Martínez, G., Iglesias-Martínez, M. J., & Lozano-Cabezas, I. (2023). A qualitative study on barriers in learning opportunities in Ecuadorian higher education. Societies, 13(3), 56. https://doi.org/10.3390/soc13030056
Susnjak, T., Ramaswami, G. S., & Mathrani, A. (2022). Learning analytics dashboard: A tool for providing actionable insights to learners. International Journal of Educational Technology in Higher Education, 19, Article 12. https://doi.org/10.1186/s41239-021-00313-7
Utamachant, P., Anutariya, C., & Pongnumkul, S. (2023). i-Ntervene: Applying an evidence-based learning analytics intervention to support computer programming instruction. Smart Learning Environments, 10, Article 37. https://doi.org/10.1186/s40561-023-00257-7
Viberg, O., Mutimukwe, C., & Grönlund, Å. (2022). Privacy in learning analytics research: Understanding the field to improve practice. Journal of Learning Analytics, 9(3), 169–182. https://doi.org/10.18608/jla.2022.7751
Villar, R., & Andrade, R. (2024). Student dropout prediction: A comparative study of supervised machine learning algorithms. Discover Artificial Intelligence, 4, Article 15. https://doi.org/10.1007/s44163-023-00079-z
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Mariuxi Lissette Arroyo Montaño, Elayne Yanin Tenorio Canchingre, Sara Sophie Mendoza Hernández, Rita Jesús Ramírez Guerrero, Karen Gabriela Perugachi Montaño
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Eres libre de:
- Compartir : copiar y redistribuir el material en cualquier medio o formato
- Adaptar : remezclar, transformar y desarrollar el material
- El licenciante no puede revocar estas libertades siempre y cuando usted cumpla con los términos de la licencia.
En los siguientes términos:
- Atribución : Debe otorgar el crédito correspondiente , proporcionar un enlace a la licencia e indicar si se realizaron cambios . Puede hacerlo de cualquier manera razonable, pero no de ninguna manera que sugiera que el licenciante lo respalda a usted o a su uso.
- No comercial : no puede utilizar el material con fines comerciales .
- CompartirIgual — Si remezcla, transforma o construye sobre el material, debe distribuir sus contribuciones bajo la misma licencia que el original.
- Sin restricciones adicionales : no puede aplicar términos legales ni medidas tecnológicas que restrinjan legalmente a otros hacer algo que la licencia permite.
